Allocation
A memory allocation handle.
|
BuiltinOpResolver |
BuiltinOpResolverWithoutDefaultDelegates |
BuiltinOpResolverWithXNNPACK |
ErrorReporter
A functor that reports error to supporting system.
|
ExternalCpuBackendContext |
FlatBufferModel |
FlatBufferModelBase
An RAII object that represents a read-only tflite model, copied from disk,
or mmapped.
|
InitializationStatus
WARNING: Experimental interface, subject to change.
|
Interpreter |
Interpreter.Check_cancelled_func_Pointer
\warning This is an experimental API and subject to change.
|
InterpreterOptions
Options class for Interpreter .
|
IntIntPair |
IntIntPairVector |
IntIntPairVectorVector |
IntIntPairVectorVector.Iterator |
IntResourceBaseMap |
IntResourceBaseMap.Iterator |
MutableOpResolver
An OpResolver that is mutable, also used as the op in gen_op_registration.
|
NodeSubset |
NodeSubsetVector |
NodeSubsetVector.Iterator |
OperatorsCache |
OpResolver
Abstract interface that returns TfLiteRegistrations given op codes or custom
op names.
|
Profiler |
RegistrationNodePair |
RegistrationNodePairVector |
ResourceBase
WARNING: Experimental interface, subject to change.
|
RootProfiler
A root profiler instance installed in TFLite runtime.
|
ScopedProfile |
SignatureRunner
runner->Invoke();
/**
|
SizeTSizeTMap |
SizeTSizeTMap.Iterator |
StderrReporter |
StringIntMap |
StringIntMap.Iterator |
StringStringMap |
StringStringMap.Iterator |
StringVector |
StringVector.Iterator |
Subgraph |
Subgraph.Check_cancelled_func_Pointer |
Subgraph.SubgraphAllocInfo |
SubgraphDelegationMetadata |
SubgraphVector |
SubgraphVector.Iterator |
TelemetryProfiler |
TelemetryStatusCode |
TfLiteAffineQuantization
Parameters for asymmetric quantization across a dimension (i.e per output
channel quantization).
|
TfLiteBFloat16
bfloat16 data type compatible with the Google Brain definition.
|
TfLiteComplex128
Double-precision complex data type compatible with the C99 definition.
|
TfLiteComplex64
Single-precision complex data type compatible with the C99 definition.
|
TfLiteContext
TfLiteContext allows an op to access the tensors.
|
TfLiteContext.AcquireSubgraphContext_TfLiteContext_int_PointerPointer
Retrieves the corresponding TfLiteContext of a subgraph that the given
subgraph_index points to and switches to the delegate context for that
subgraph.
|
TfLiteContext.AddTensors_TfLiteContext_int_IntPointer
Add tensors_to_add tensors, preserving pre-existing Tensor entries.
|
TfLiteContext.AllocateBufferForEval_TfLiteContext_long_PointerPointer
Allocate a buffer which will be deallocated right after invoke phase.
|
TfLiteContext.AllocatePersistentBuffer_TfLiteContext_long
Allocate persistent buffer which has the same life time as the
interpreter.
|
TfLiteContext.GetEvalTensor_TfLiteContext_int
Returns a TfLiteEvalTensor struct for a given index.
|
TfLiteContext.GetExecutionPlan_TfLiteContext_PointerPointer
The execution plan contains a list of the node indices in execution
order.
|
TfLiteContext.GetExternalContext_TfLiteContext_int
Access external contexts by type.
|
TfLiteContext.GetModelMetadata_TfLiteContext_BytePointer_PointerPointer_SizeTPointer
Retrieves named metadata buffer from the TFLite model.
|
TfLiteContext.GetNodeAndRegistration_TfLiteContext_int_PointerPointer_PointerPointer
Get a Tensor node by node_index.
|
TfLiteContext.GetScratchBuffer_TfLiteContext_int
Get the scratch buffer pointer.
|
TfLiteContext.GetTensor_TfLiteContext_int
Returns a TfLiteTensor struct for a given index.
|
TfLiteContext.PreviewDelegatePartitioning_TfLiteContext_TfLiteIntArray_PointerPointer_IntPointer
This method provides a preview of post-delegation partitioning.
|
TfLiteContext.ReleaseSubgraphContext_TfLiteContext_int
Releases the subgraph context by switching back to the TFLite kernel
context for the subgraph that the given subgraph_index points to.
|
TfLiteContext.ReplaceNodeSubsetsWithDelegateKernels_TfLiteContext_TfLiteRegistration_TfLiteIntArray_TfLiteDelegate
Replace ops with one or more stub delegate operations.
|
TfLiteContext.RequestScratchBufferInArena_TfLiteContext_long_IntPointer
Request a scratch buffer in the arena through static memory planning.
|
TfLiteContext.ResizeTensor_TfLiteContext_TfLiteTensor_TfLiteIntArray
Request memory pointer be resized.
|
TfLiteContext.ResizeTensorExplicit_TfLiteContext_TfLiteTensor_int_IntPointer
Resize the memory pointer of the tensor .
|
TfLiteContext.SetExternalContext_TfLiteContext_int_TfLiteExternalContext
Set the value of a external context.
|
TfLiteCustomAllocation
Defines a custom memory allocation not owned by the runtime.
|
TfLiteDelegate
WARNING: This is an experimental interface that is subject to change.
|
TfLiteDelegate.CopyFromBufferHandle_TfLiteContext_TfLiteDelegate_int_TfLiteTensor
Copy the data from delegate buffer handle into raw memory of the given
tensor .
|
TfLiteDelegate.CopyToBufferHandle_TfLiteContext_TfLiteDelegate_int_TfLiteTensor
Copy the data from raw memory of the given tensor to delegate buffer
handle.
|
TfLiteDelegate.FreeBufferHandle_TfLiteContext_TfLiteDelegate_IntPointer
Free the Delegate Buffer Handle.
|
TfLiteDelegate.Prepare_TfLiteContext_TfLiteDelegate
Invoked by ModifyGraphWithDelegate .
|
TfLiteDelegateParams
WARNING: This is an experimental interface that is subject to change.
|
TfLiteDelegatePtrVector |
TfLiteDelegatePtrVector.Iterator |
TfLiteDimensionMetadata
Metadata to encode each dimension in a sparse tensor.
|
TfLiteEvalTensor
Light-weight tensor struct for TF Micro runtime.
|
TfLiteExternalContext
An external context is a collection of information unrelated to the TF Lite
framework, but useful to a subset of the ops.
|
TfLiteExternalContext.Refresh_TfLiteContext |
TfLiteFloat16
Half precision data type compatible with the C99 definition.
|
TfLiteFloatArray
Fixed size list of floats.
|
TfLiteIntArray
Fixed size list of integers.
|
TfLiteInternalBackendContext |
TfLiteNode
A structure representing an instance of a node.
|
TfLiteOpaqueContext
TfLiteOpaqueContext is an opaque version of TfLiteContext;
|
TfLiteOpaqueDelegateBuilder
TfLiteOpaqueDelegateBuilder is used for constructing
TfLiteOpaqueDelegate , see TfLiteOpaqueDelegateCreate in c_api_opaque.h.
|
TfLiteOpaqueDelegateBuilder.CopyFromBufferHandle_TfLiteOpaqueContext_TfLiteOpaqueDelegateStruct_Pointer_int_TfLiteOpaqueTensor
Copies the data from delegate buffer handle into raw memory of the given
tensor .
|
TfLiteOpaqueDelegateBuilder.CopyToBufferHandle_TfLiteOpaqueContext_TfLiteOpaqueDelegateStruct_Pointer_int_TfLiteOpaqueTensor
Copies the data from raw memory of the given tensor to delegate buffer
handle.
|
TfLiteOpaqueDelegateBuilder.FreeBufferHandle_TfLiteOpaqueContext_TfLiteOpaqueDelegateStruct_Pointer_IntPointer
Frees the Delegate Buffer Handle.
|
TfLiteOpaqueDelegateBuilder.Prepare_TfLiteOpaqueContext_TfLiteOpaqueDelegateStruct_Pointer
Invoked by ModifyGraphWithDelegate.
|
TfLiteOpaqueDelegateParams
WARNING: This is an experimental interface that is subject to change.
|
TfLiteOpaqueDelegateStruct
TfLiteOpaqueDelegateStruct: unconditionally opaque version of
TfLiteDelegate; allows delegation of nodes to alternative backends.
|
TfLiteOpaqueNode
TfLiteOpaqueNode is an opaque version of TfLiteNode;
|
TfLiteOpaqueTensor
TfLiteOpaqueTensor is an opaque version of TfLiteTensor;
|
TfLiteOperator
TfLiteOperator is an opaque version of TfLiteRegistration,
and is used for registering custom ops.
|
TfLitePtrUnion
A union of pointers that points to memory for a given tensor.
|
TfLiteQuantization
Structure specifying the quantization used by the tensor, if-any.
|
TfLiteQuantizationParams
Legacy.
|
TfLiteRegistration
TfLiteRegistration defines the implementation of an operation
(a built-in op, custom op, or custom delegate kernel).
|
TfLiteRegistration_V1
\private
Old version of TfLiteRegistration to maintain binary backward
compatibility.
|
TfLiteRegistration_V1.Free_TfLiteContext_Pointer |
TfLiteRegistration_V1.Init_TfLiteContext_BytePointer_long |
TfLiteRegistration_V1.Invoke_TfLiteContext_TfLiteNode |
TfLiteRegistration_V1.Prepare_TfLiteContext_TfLiteNode |
TfLiteRegistration_V1.Profiling_string_TfLiteContext_TfLiteNode |
TfLiteRegistration_V2
\private
Old version of TfLiteRegistration to maintain binary backward
compatibility.
|
TfLiteRegistration_V2.Free_TfLiteContext_Pointer |
TfLiteRegistration_V2.Init_TfLiteContext_BytePointer_long |
TfLiteRegistration_V2.Invoke_TfLiteContext_TfLiteNode |
TfLiteRegistration_V2.Prepare_TfLiteContext_TfLiteNode |
TfLiteRegistration_V2.Profiling_string_TfLiteContext_TfLiteNode |
TfLiteRegistration_V3
\private
Old version of TfLiteRegistration to maintain binary backward
compatibility.
|
TfLiteRegistration_V3.Free_TfLiteContext_Pointer |
TfLiteRegistration_V3.Init_TfLiteContext_BytePointer_long |
TfLiteRegistration_V3.Invoke_TfLiteContext_TfLiteNode |
TfLiteRegistration_V3.Prepare_TfLiteContext_TfLiteNode |
TfLiteRegistration_V3.Profiling_string_TfLiteContext_TfLiteNode |
TfLiteRegistration.Free_TfLiteContext_Pointer
The pointer buffer is the data previously returned by an init
invocation.
|
TfLiteRegistration.Init_TfLiteContext_BytePointer_long
Initializes the op from serialized data.
|
TfLiteRegistration.Invoke_TfLiteContext_TfLiteNode
Execute the node (should read node->inputs and output to
node->outputs ).
|
TfLiteRegistration.Prepare_TfLiteContext_TfLiteNode
prepare is called when the inputs this node depends on have been resized.
|
TfLiteRegistration.Profiling_string_TfLiteContext_TfLiteNode
profiling_string is called during summarization of profiling information
in order to group executions together.
|
TfLiteSparsity
Parameters used to encode a sparse tensor.
|
TfLiteTelemetryProfilerStruct |
TfLiteTelemetryProfilerStruct.ReportBeginOpInvokeEvent_TfLiteTelemetryProfilerStruct_BytePointer_long_long |
TfLiteTelemetryProfilerStruct.ReportEndOpInvokeEvent_TfLiteTelemetryProfilerStruct_int |
TfLiteTelemetryProfilerStruct.ReportOpInvokeEvent_TfLiteTelemetryProfilerStruct_BytePointer_long_long_long |
TfLiteTelemetryProfilerStruct.ReportSettings_TfLiteTelemetryProfilerStruct_BytePointer_TfLiteTelemetrySettings |
TfLiteTelemetryProfilerStruct.ReportTelemetryEvent_TfLiteTelemetryProfilerStruct_BytePointer_long |
TfLiteTelemetryProfilerStruct.ReportTelemetryOpEvent_TfLiteTelemetryProfilerStruct_BytePointer_long_long_long |
TfLiteTelemetrySettings |
TfLiteTensor
A tensor in the interpreter system which is a wrapper around a buffer of
data including a dimensionality (or NULL if not currently defined).
|
TfLiteTensorDeleter |
TfLiteVerifier
Abstract interface that verifies whether a given model is legit.
|
VariantData |